Moonshot AIMultimodal modelKimi K3.1 Pro
Moonshot AI multimodal model for research, coding, writing and image understanding.
Model availability and access depend on your workspace and plan.
Kimi K3.1 ProAbout the model
Kimi K3.1 Pro, explained.
Moonshot AI multimodal model for research, coding, writing and image understanding.
Supported capabilities
- Chat
- Reasoning
- Analysis
- Research
- Coding
- Writing
- Vision
What you get back. The response appears directly in your Relam chat, where you can continue the conversation.
Capabilities & limits
Inside Kimi K3.1 Pro.
Chat
Ask questions, give instructions and continue with follow-up messages in a conversation.
Analysis
Ask the model to examine supplied information and develop a written analysis.
Research
Kimi K3.1 Pro lists research among its supported capabilities.
Coding
Use the model for code-focused questions and programming tasks. Review generated code before using it.
Writing
Work on written drafts, revisions and wording through conversational instructions.
Vision
The catalogue lists image understanding as a supported model capability. Available attachment controls depend on your workspace.
Context window
Kimi K3.1 Pro has a 1,048,576-token context window. This is the model’s capacity for the text it considers in a request, including prompts and conversation context. Tokens are pieces of text, rather than a word or page count. The amount of context sent by your workspace can be lower.
Questions & answers
More about Kimi K3.1 Pro.
Moonshot AI multimodal model for research, coding, writing and image understanding.
Moonshot AI is the vendor behind Kimi K3.1 Pro, a multimodal model available in the Relam catalogue.
Ask questions, give instructions and continue with follow-up messages in a conversation.
Ask the model to examine supplied information and develop a written analysis.
Kimi K3.1 Pro lists research among its supported capabilities.
Use the model for code-focused questions and programming tasks. Review generated code before using it.
Work on written drafts, revisions and wording through conversational instructions.
The catalogue lists image understanding as a supported model capability. Available attachment controls depend on your workspace.
Kimi K3.1 Pro has a 1,048,576-token context window. This is the model’s capacity for the text it considers in a request, including prompts and conversation context. Tokens are pieces of text, rather than a word or page count. The amount of context sent by your workspace can be lower.
The catalogue sets a maximum output of 8,192 tokens for Kimi K3.1 Pro. This is the response budget, distinct from its context window. Responses can be shorter depending on your request and the limits applied by your workspace.
Kimi K3.1 Pro is listed as a reasoning-capable model. Its configured reasoning levels are low, medium, high. The default level is medium. Available controls depend on your workspace.
Open your Relam workspace and look for Kimi K3.1 Pro in the multimodal model selector. Available models, controls and access depend on your workspace and plan.